Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1838 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.4730. Min Act: -0.0001

Data Index: 66639 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.3604. Min Act: -0.0001

Data Index: 182784 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.3891. Min Act: -0.0001

Data Index: 1142828 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.3298. Min Act: -0.0001

Data Index: 227274 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2521. Min Act: -0.0001

Data Index: 1170843 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2599. Min Act: -0.0001

Data Index: 332219 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2541. Min Act: -0.0001

Data Index: 528750 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2376. Min Act: -0.0001

Data Index: 1179651 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2795. Min Act: -0.0001

Data Index: 1041933 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2691. Min Act: -0.0001

Data Index: 142668 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.3363. Min Act: -0.0001

Data Index: 716885 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2561. Min Act: -0.0001

Data Index: 1332730 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.3343. Min Act: -0.0001

Data Index: 54208 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2477. Min Act: -0.0001

Data Index: 342924 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2856. Min Act: -0.0001

Data Index: 681950 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2000. Min Act: -0.0001

Data Index: 636013 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.1947. Min Act: -0.0001

Data Index: 1110755 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2620. Min Act: -0.0001

Data Index: 178991 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2285. Min Act: -0.0001

Data Index: 1344889 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.4730. Min Range: -1.4730

Max Act: 1.2195. Min Act: -0.0001

Data Index: 1184968 (C4 (Web Text))

Max Activating Token Index: 940